Add Laguna XS.2.1 DFlash drafter support (#46853)
Signed-off-by: Adam Baranowski <adam.baranowski@poolside.ai>
This commit is contained in:
@@ -28,6 +28,7 @@ from vllm.model_executor.model_loader import get_model
|
||||
from vllm.model_executor.models import supports_multimodal
|
||||
from vllm.model_executor.models.deepseek_eagle3 import Eagle3DeepseekV2ForCausalLM
|
||||
from vllm.model_executor.models.interfaces import SupportsMultiModal
|
||||
from vllm.model_executor.models.laguna_dflash import DFlashLagunaForCausalLM
|
||||
from vllm.model_executor.models.llama_eagle3 import Eagle3LlamaForCausalLM
|
||||
from vllm.model_executor.models.qwen3_dflash import DFlashQwen3ForCausalLM
|
||||
from vllm.model_executor.models.qwen3_eagle3 import Eagle3Qwen3ForCausalLM
|
||||
@@ -533,6 +534,7 @@ class SpecDecodeBaseProposer:
|
||||
Eagle3DeepseekV2ForCausalLM,
|
||||
DFlashQwen3ForCausalLM,
|
||||
Eagle3Qwen3ForCausalLM,
|
||||
DFlashLagunaForCausalLM,
|
||||
),
|
||||
)
|
||||
target_hidden_states = self.model.combine_hidden_states(
|
||||
|
||||
Reference in New Issue
Block a user